Analysis of the exhaust hydrogen characteristics of high-compression ratio, ultra-lean, hydrogen spark-ignition engine using advanced regression algorithms

Hydrogen is a leading alternative fuel for eliminating the carbon emissions of internal combustion engines. Moreover, the use of hydrogen improves the combustion owing to its high flame speed. The hydrogen selective catalytic reduction is a promising solution for the reduction of nitric oxides (NOx), which is the sole regulated gas species in hydrogen-fueled internal combustion engines. In the present study, hydrogen and NOx emissions, the crucial species for the catalyst performance, were investigated using a heavy-duty, hydrogen spark-ignition engine. The ratio of H2 to NOx was above 100 at the excess air ratio (lambda) of 2.5 or higher. Three-dimensional, numerical simulation showed that the in-cylinder hydrogen distribution was dependent on the engine load and the lambda value. A regression analysis showed that the exhaust hydrogen quantity had a strong correlation with the seven parameters, namely engine speed, the gross indicated effective pressure (IMEPg), lambda, spark timing, total combustion duration, peak in-cylinder temperature, and peak pressure rise rate. Among these parameters, the IMEPg and the lambda value exhibited the highest weights in a neighborhood component analysis. The regression model with the seven features exhibited the highest R2 value of 0.94 with the squared exponential Gaussian process regression. The proposed prediction model can contribute to not only reducing NOx emission with aftertreatment, but also maximizing the thermal efficiency of hydrogen-fueled in-ternal combustion engines.